© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110987
    Prev
    Next
    INDEX
    Explanations

    script tags with source attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moyen
    -0.93
     css
    -0.89
     Senado
    -0.83
     presencia
    -0.81
    zember
    -0.80
    leder
    -0.78
     frontera
    -0.77
     Tổng
    -0.77
    css
    -0.77
    还可以
    -0.76
    POSITIVE LOGITS
     especially
    1.14
    script
    1.05
     script
    1.02
     specifically
    0.86
     particularly
    0.82
     as
    0.82
     often
    0.81
    を描
    0.81
     init
    0.79
    ;(
    0.79
    Activations Density 0.009%

    No Known Activations